# AIGT Detection on Cross-Domain (AI -\> Human) Source: [AIGT Detection on Cross-Domain (AI -\> Human)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:24.936Z Evaluation of AI Generated Text (AIGT) detection performance on a cross-domain dataset, specifically focusing on the scenario where AI outputs are compared against Human references. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | AIGT Detection | | Dataset (including any stated split) | cross-domain AIGT detection AI -\> Human | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Overall Accuracy](): Higher is better; unit: PERCENT. - [AUA Score](): Higher is better; unit: SCALAR. - [ASR Rate](): Higher is better; unit: PERCENT. - [ANQ Metric](): Higher is better; unit: SCALAR. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ChatGPT-Detector | 96 | Not recorded | 68fa73e41e209131cea5eb76 | | SeqXGPT | 93 | Not recorded | 68fa73e41e209131cea5eb76 | | DeBERTa | 91.5 | Not recorded | 68fa73e41e209131cea5eb76 | | RoBERTa | 90.5 | Not recorded | 68fa73e41e209131cea5eb76 | | Flooding | 90 | Not recorded | 68fa73e41e209131cea5eb76 | | RDrop | 89.5 | Not recorded | 68fa73e41e209131cea5eb76 | | RanMASK | 89 | Not recorded | 68fa73e41e209131cea5eb76 | | SCRN | 86.5 | Not recorded | 68fa73e41e209131cea5eb76 | | RMLM | 81.5 | Not recorded | 68fa73e41e209131cea5eb76 | | BERT | 80 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Rank | 72 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Likelihood | 67 | Not recorded | 68fa73e41e209131cea5eb76 | | GLTR | 66.5 | Not recorded | 68fa73e41e209131cea5eb76 | | Entropy | 43.5 | Not recorded | 68fa73e41e209131cea5eb76 | ### ChatGPT-Detector Overall Accuracy: 96. Result ID: 699311603a6c3148491377be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### SeqXGPT Overall Accuracy: 93. Result ID: 699311603a6c3148491377ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### DeBERTa Overall Accuracy: 91.5. Result ID: 699311603a6c3148491377bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### RoBERTa Overall Accuracy: 90.5. Result ID: 699311603a6c3148491377bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### Flooding Overall Accuracy: 90. Result ID: 699311603a6c3148491377bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### RDrop Overall Accuracy: 89.5. Result ID: 699311603a6c3148491377c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### RanMASK Overall Accuracy: 89. Result ID: 699311603a6c3148491377c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### SCRN Overall Accuracy: 86.5. Result ID: 699311603a6c3148491377c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### RMLM Overall Accuracy: 81.5. Result ID: 699311603a6c3148491377c2. [Reporting paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### BERT Overall Accuracy: 80. Result ID: 699311603a6c3148491377bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### Log-Rank Overall Accuracy: 72. Result ID: 699311603a6c3148491377b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### Log-Likelihood Overall Accuracy: 67. Result ID: 699311603a6c3148491377b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### GLTR Overall Accuracy: 66.5. Result ID: 699311603a6c3148491377b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. ### Entropy Overall Accuracy: 43.5. Result ID: 699311603a6c3148491377b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack":"PWWS"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.